gro: Optimise Ethernet header comparison

This patch optimises the Ethernet header comparison to use 2-byte
and 4-byte xors instead of memcmp.  In order to facilitate this,
the actual comparison is now carried out by the callers of the
shared dev_gro_receive function.

This has a significant impact when receiving 1500B packets through
10GbE.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 28 insertions, 0 deletions

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 1cb0f0b90926..a1f17abba7dc 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -184,4 +184,25 @@ static inline unsigned compare_ether_addr_64bits(const u8 addr1[6+2],
 }
 #endif  /* __KERNEL__ */
 
+/**
+ * compare_ether_header - Compare two Ethernet headers
+ * @a: Pointer to Ethernet header
+ * @b: Pointer to Ethernet header
+ *
+ * Compare two ethernet headers, returns 0 if equal.
+ * This assumes that the network header (i.e., IP header) is 4-byte
+ * aligned OR the platform can handle unaligned access.  This is the
+ * case for all packets coming into netif_receive_skb or similar
+ * entry points.
+ */
+
+static inline int compare_ether_header(const void *a, const void *b)
+{
+        u32 *a32 = (u32 *)((u8 *)a + 2);
+        u32 *b32 = (u32 *)((u8 *)b + 2);
+
+        return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) |
+               (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]);
+}
+
 #endif  /* _LINUX_ETHERDEVICE_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9ee344bc6c13..355662aac940 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1117,6 +1117,13 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb)
         NAPI_GRO_CB(skb)->data_offset = 0;
 }
 
+static inline void *skb_gro_mac_header(struct sk_buff *skb)
+{
+        return skb_mac_header(skb) < skb->data ? skb_mac_header(skb) :
+               page_address(skb_shinfo(skb)->frags[0].page) +
+               skb_shinfo(skb)->frags[0].page_offset;
+}
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
                                   unsigned short type,
                                   const void *daddr, const void *saddr,